INDEX

Explanations

words related to things slowing down or becoming slower

oai_token-act-pair · gpt-3.5-turbo

expressions that indicate the concept of slowing or a decrease in pace or progress

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esan

-0.93

 Networks

-0.78

 Representatives

-0.76

oral

-0.74

asel

-0.73

ilial

-0.73

 Institution

-0.73

rists

-0.72

NBA

-0.71

çīĪ

-0.70

POSITIVE LOGITS

 slows

1.33

 slowing

1.33

 slowed

1.25

 slowdown

1.18

 slower

1.14

 cooker

1.14

 speeding

1.06

 paced

1.05

 slow

1.01

 pace

1.01

Activations Density 0.010%

words related to things slowing down or becoming slower

expressions that indicate the concept of slowing or a decrease in pace or progress

No Comments

No Known Activations